In addition to our call for papers at our third bridge on Continual Causality at AAAI-25 we are launching the Continual Confounding: ConCon Challenge! In the ConCon challenge participants can submit contributions to solve one of two (or both) challenging scenarios surrounding the newly found… Read More »We are launching the ConCon Challenge at the Continual Causality Bridge!
we are happy to co-organize the third edition of the Continual Causality bridge at AAAI-25! Continual Causality is a full two-day event (25+26th of February 2025 at AAAI-25 in Philadelphia, USA): a “bridge” with the aim of bringing together the research fields of continual learning and causality. Beyond scientific advance, one primary goal is to… Read More »The Continual Causality Bridge is back for round 3
Our paper “Distribution-Aware Replay for Continual MRI Segmentation” got accepted the Workshop Personalized Incremental Learning in Medicine at MICCAI 2024, with proceedings to be published in Lecture Notes in Computer Science (LNCS), Springer. In the paper, we demonstrate that a small generative model (a variational… Read More »”Distribution-Aware Replay for Continual MRI Segmentation” accepted at PILM-MICCAI 2024
We are very honored and grateful that our paper “Deep Classifier Mimicry without Data Access” has received an Outstanding Student Paper Highlight award at AISTATS 2024. In the paper, we introduce a method to distill a deep classifiers knowledge without making assumptions on model structure… Read More »We received the AISTATS 2024 outstanding student paper highlight
Our paper “Masked Autoencoders are Efficient Continual Federated Learners” got accepted for publication at the Conference on Lifelong Learning Agents (CoLLAs) 2024! In the paper we investigate the challenging task of unsupervised continual learning in federated (distributed) scenarios. Our key motivation is that even if… Read More »“Masked Autoencoders are Efficient Continual Federated Learners” accepted at CoLLAs 2024
Our paper “Deep Classifier Mimicry without Data Access” got accepted at the International Conference on Artificial Intelligence and Statistics (AISTATS) 2024. We are honored to have been selected for an oral presentation!
Our paper “Adaptive Rational Activations to Boost Deep Reinforcement Learning” was accepted at the International Conference on Learning Representations (ICLR) 2024. We are honored to have been selected for a spotlight presentation!
Following the in-person European Summer School on AI (ESSAI) in Ljubljana, Slovenia from July 24-28. 2023, the recordings for the 5-day course on “Machine Learning Beyond Static Datasets” have now been made publicly available.
We are delighted to welcome Qi Li as a research assistant in the OWLL group. In the process of working on her Master’s degree, Qi will spend the next year exploring continual learning models for climate within the recently granted project CAIMAN: “Continual Artificial Intelligence… Read More »Qi Li joins as research assistant for project CAIMAN
Our paper title “Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation” has been accepted for publication at the Winter Conference on Applications of Computer Vision (WACV). The paper tackles the challenging real-world task to semantically segment cracks in concrete infrastructure.… Read More »“Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation” accepted at WACV 2024
